The Meertens Tune Collections
With the Meertens Tune Collections (MTC) the Meertens Institute provides a rich set of collections of musical data for research purposes, such as musicological investigations or music information retrieval tasks. Over the past decades, these data have been collected in the Database of Dutch Songs. The online interface of the Database of Dutch songs provides access at the level of individual records through extensive search and browse functionality.
With the MTC, several collections are provided as a whole. MTC currently consist of the following collections:
| Name||Description||data types||version|
| MTC-OGLAUDIO||Collection Onder de groene linde: 7178 audio recordings collected by Dutch field workers during the 1950s-1980s.||mp3||1.0|
| MTC-OGLSCANS||Scans of 3754 transcriptions of recordings from Onder de groene linde as made during the 1950s-1980s. The music is hand-written, the lyrics are typed.||jpg||1.0|
| MTC-FS||4120 digitally encoded vocal folk songs both from Onder de groene linde (2503) and from various related written sources (1617).||**kern, midi, lilypond, png, pdf, txt||1.0|
| MTC-INST||2368 digitally encoded instrumental tunes from 18th-century Dutch manuscripts and printed scores.||**kern, midi, lilypond, png, pdf||1.0|
| MTC-ANN||Annotated Corpus: 360 melodies used in various publications.||**kern, midi, png, pdf||1.0|
| MTC-ANN||Annotated Corpus: 360 melodies used in various publications.||**kern, midi,lilypond, png, pdf, txt||1.1|
| MTC-ANN||Annotated Corpus: 360 melodies used in various publications.||**kern, midi,lilypond, png, pdf, txt||2.0|
| MTC-ANN||Annotated Corpus: 360 melodies used in various publications.||**kern, midi,lilypond, png, pdf, txt||2.0.1|
| MTC-LC||Large Corpus: 4830 melodies used in various publications.||**kern, midi||1.0|
MTC-LC has a large overlap with both MTC-FS and MTC-INST. It is provided because it has been used for various research publications. MTC-ANN is a subset of MTC-LC that is carefully selected for small scale experiments and that has been annotated concerning melodic similarity and motif occurrences. It contains 26 tune families.
A concise description of the MTC is available in the following reports:
Van Kranenburg, Peter & Martine de Bruin & Louis P. Grijp & Frans Wiering. "The Meertens Tune Collections". Meertens Online Reports, No. 2014-1. Amsterdam: Meertens Institute, 2014. download pdf.
Van Kranenburg, Peter & Berit Janssen & Anja Volk. "The Meertens Tune Collections: The Annotated Corpus (MTC-ANN) Versions 1.1 and 2.0.1". Meertens Online Reports, No. 2016-1. Amsterdam: Meertens Institute, 2016. download pdf.
If you use this data for a research paper, please cite one of these reports.
The melodies are provided in **kern format. Furthermore, pdf and png files of the scores are provided, as well as midi files, lilypond sources, and separate files with the (syllablized) lyrics.
The collections come with a wealth of meta data. Some highlights: most melodies have a tune family label, which connects variants of the same tune. Several levels of membership are indicated. For the audio recordings, we provide date and location (longitude and latitude) of recording and date of birth and place of birth of the singer(s). For all folk song melodies, phrase endings are indicated. Meta data is provided in comma-separated text files (csv) in UTF8 encoding.
Some Music Information Retrieval tasks that could be addressed with this data set:
- Melodic Segmentation - using the phrase markers
- Melodic Similarity - using the tune family labels
- Geographic Clustering - using geographic information of singers and recordings
- Audio-Score alignment - using mp3 and scans
- Singer classification - using singer names
- Optical Music Recognition - using the scans
- Pattern discovery
- Lyric-Audio alignment
- And many more... your imagination is the limit
To get a quick idea of the contents of MTC, a sample dataset containing
a small subset of each collection is available for download:
To download follow this link: download form. We appreciate when you drop us your name, a comment (optionally) and your email address (optionally). The email addresses will exclusively be used for future notifications about MTC, and will under no circumstance be shared with third parties.
The Meertens Tune Collections were demonstrated during the 15th and 16th International Society for Music Information Retrieval Conferences.
Download poster 2014. Download poster 2015.
Permament and sustainable storage of MTC is guaranteed by the Meertens Institute.
Peter van Kranenburg, firstname.lastname@example.org
Meertens Tune Collections by Meertens Institute is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.
Based on a work at www.liederenbank.nl/mtc.
The Meertens Tune Collections have been used in the following publications:
- Panteli, M & S. Dixon. (2016). On the evaluation of rhythmic and melodic descriptors for music similarity. Proceedings of the 17th International Society for Music Information Retrieval Conference, New York. pp. 468-474.
- Boot, P. & A. Volk & W.B. de Haas. (2016). Evaluating the Role of Repeated Patterns in Folk Song Classification and Compression. Journal of New Music Research 45 (3), pp. 223-238.
- Bountouridis, D. & H.V. Koops & F. Wiering & R.C. Veltkamp. (2016). Music Outlier Detection Using Multiple Sequence Alignment and Independent Ensembles. Similarity Search and Applications - 9th International Conference, SISAP 2016, Tokyo, Japan, October 24-26, 2016, Proceedings. pp. 286-300.
- Goienetxea, I. & K. Neubarth & D. Conklin. (2016). Melody classification with pattern covering. MML 2016: 9th International Workshop on Machine Learning and Music. pp. 26-30.
- Van Kranenburg, P. & D. Conklin. (2016). A Pattern Mining Approach to Study a Collection of Dutch Folk-Songs. Proceedings of the Sixth International Workshop on Folk Music Analysis, Dublin. pp 71-73.
- Van Balen, J. (2016). Audio Description and Corpus Analysis of Popular Music. Ph.D. diss., Utrecht University.
- Rodríguez-López, M. (2016). Automatic Melody Segmentation. Ph.D. diss., Utrecht University.
- Olthof, M. & B. Janssen & H. Honing. (2015). The Role Of Absolute Pitch Memory In The Oral Transmission of Folksongs. Empirical Music Review 10 (3), pp. 161-174.
- Rodríguez-López, M.E. & A. Volk. (2015). Selective Acquisition Techniques for Enculturation-Based Melodic Phrase Segmentation". Proceedings of the 16th International Society for Music Information Retrieval Conference, Malaga. pp. 218-224.
- Boot, P. (2015). Using Discovered and Annotated Patterns as Compression Method for determining Similarity between Folk Songs. Master Thesis, Utrecht University.
- Janssen, B. & P. van Kranenburg. (2015). A Comparison of Symbolic Similarity Measures for Finding Occurrences of Melodic Segments. Proceedings of the 16th International Society for Music Information Retrieval Conference, Malaga. pp. 659-672.
- Van Kranenburg, P. & F. Karsdorp. (2014). Cadence Detection in Western Traditional Stanzaic Songs using Melodic and Textual Features. Proceedings of the 15th International Society for Music Information Retrieval Conference, Taipei. pp. 391-396.
- Van Kranenburg, P. & A. Volk & F. Wiering. (2013). A Comparison between Global and Local Features for Computational Classification of Folk Song Melodies. Journal of New Music Research 42 (1), pp. 1-18.
- Conklin, D. (2013). Fusion functions for multiple viewpoints. MML 2013: International Workshop on Machine Learning and Music, Prague.
- Velarde, G., T. Weyde & D. Meredith. (2013). An approach to melodic segmentation and classification based on filtering with the Haar wavelet. Journal of New Music Research 42(4), pp. 325-345.
- Hillewaere, R., B. Manderick, and D. Conklin. (2014). Alignment methods for folk tune classification. Spiliopoulou, M. et al., (eds). Data Analysis, Machine Learning and Knowledge Discovery, Studies in Classification, Data Analysis, and Knowledge Organization. pp. 369-378.
- Van Kranenburg, P. & A. Volk & F. Wiering. (2012). On Identifying Folk Song Melodies Employing Recurring Motifs. Proceedings of the 12th International Conference on Music Perception and Cognition and the 8th Triennial Conference of the European Society for the Cognitive Sciences of Music, Thessaloniki. pp. 1057-1062.
- Volk, A. & P. van Kranenburg. (2012). Melodic similarity among folk songs: An annotation study on similarity-based categorization in music. Musicae Scientiae 16, issue 3, pp. 317-339.
- Van Kranenburg, P. & A. Volk & F. Wiering. (2011). On Operationalizing the Musicological Concept of Tune Family for Computational Modeling. Maegaard, B (ed.). Proceedings of Supporting Digital Humanities: Answering the unaskable. Kopenhagen.
- Van Kranenburg, P. (2010). A Computational Approach to Content-Based Retrieval of Folk Song Melodies. Ph.D. diss., Utrecht University.
- Van Kranenburg, P. & G. Tzanetakis. (2010). A Computational Approach to the Modeling and Employment of Cognitive Units of Folk Song Melodies using Audio Recordings. Proceedings of the 11th International Conference on Music Perception and Cognition, Seattle.
Last change: November 14th, 2016